Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2874 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.4721. Min Act: -0.0001

Data Index: 996548 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.4362. Min Act: -0.0001

Data Index: 741130 (C4 (Web Text))

Max Activating Token Index: 267

Text #2

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.4319. Min Act: -0.0001

Data Index: 1074038 (C4 (Web Text))

Max Activating Token Index: 173

Text #3

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.4317. Min Act: -0.0001

Data Index: 519761 (C4 (Web Text))

Max Activating Token Index: 319

Text #4

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.3982. Min Act: -0.0001

Data Index: 703205 (C4 (Web Text))

Max Activating Token Index: 319

Text #5

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.4161. Min Act: -0.0001

Data Index: 976614 (C4 (Web Text))

Max Activating Token Index: 451

Text #6

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.3835. Min Act: -0.0001

Data Index: 1353359 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.3894. Min Act: -0.0001

Data Index: 634364 (C4 (Web Text))

Max Activating Token Index: 247

Text #8

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.3745. Min Act: -0.0001

Data Index: 698908 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.3579. Min Act: -0.0001

Data Index: 548439 (C4 (Web Text))

Max Activating Token Index: 747

Text #10

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.3484. Min Act: -0.0001

Data Index: 1162520 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.3428. Min Act: -0.0001

Data Index: 91198 (C4 (Web Text))

Max Activating Token Index: 828

Text #12

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.3119. Min Act: -0.0001

Data Index: 1013641 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.3654. Min Act: -0.0001

Data Index: 329463 (C4 (Web Text))

Max Activating Token Index: 929

Text #14

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.3285. Min Act: -0.0001

Data Index: 573654 (C4 (Web Text))

Max Activating Token Index: 906

Text #15

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.3490. Min Act: -0.0001

Data Index: 1117256 (C4 (Web Text))

Max Activating Token Index: 414

Text #16

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.3463. Min Act: -0.0001

Data Index: 365713 (C4 (Web Text))

Max Activating Token Index: 415

Text #17

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.3440. Min Act: -0.0001

Data Index: 9973 (C4 (Web Text))

Max Activating Token Index: 726

Text #18

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.3326. Min Act: -0.0001

Data Index: 433127 (C4 (Web Text))

Max Activating Token Index: 422

Text #19

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.3429. Min Act: -0.0001

Data Index: 1234417 (C4 (Web Text))

Max Activating Token Index: 689